LiveCodeBench v6
AssessTools
A benchmark for evaluating AI models on competitive programming problems.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by model releases, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7VentureBeat AI·1/7/2026model_releaseNous Research releases open-source NousCoder-14B coding model
Nous Research has released NousCoder-14B, an open-source coding model trained in four days on 48 Nvidia B200 GPUs. The model reports 67.87% accuracy on LiveCodeBench v6 and is notable for being fully reproducible, with weights, training environment, benchmark suite, and harness published alongside the release.